The site of the Media Sphera Publishers contains materials intended solely for healthcare professionals.
By closing this message, you confirm that you are a certified medical professional or a student of a medical educational institution.

Login
EN
+7 (495) 482-4118
+7 (495) 482-0604
+8 800 101-59-87
  • (toll-free number for subscriptions)
    Mon-Fri from 10 a.m. to 6 p.m.

  • © 1998-2024
+7 (495) 482-43-29
EN
All journals
Journal
Year
Year
Search result: 0

Mishkin I.A.

National Medical Research Center for Therapy and Preventive Medicine;
Kireevsk Central District Hospital

Kontsevaya A.V.

National Medical Research Center for Therapy and Preventive Medicine

Gusev A.V.

Russian Research Institute of Health;
K-SkAI

Saharov A.A.

Renaissance Insurance Group

Drapkina O.M.

National Medical Research Center for Therapy and Preventive Medicine;
A.I. Yevdokimov Moscow State University of Medicine and Dentistry

Comparison of the predictive values of traditional cardiovascular risk assessment methods using SCORE and FRAMINGHAM scales, machine learning technologies «INTEREPID»

Authors:

Mishkin I.A., Kontsevaya A.V., Gusev A.V., Saharov A.A., Drapkina O.M.

More about the authors

Journal: Russian Journal of Preventive Medicine. 2024;27(2): 96‑102

DOI: 10.17116/profmed20242702196

Views: 676

Downloaded: 42

Download PDF (RU)
Contact the author
Table of contents

To cite this article:

Mishkin IA, Kontsevaya AV, Gusev AV, Saharov AA, Drapkina OM. Comparison of the predictive values of traditional cardiovascular risk assessment methods using SCORE and FRAMINGHAM scales, machine learning technologies «INTEREPID». Russian Journal of Preventive Medicine. 2024;27(2):96‑102. (In Russ.)
https://doi.org/10.17116/profmed20242702196

Подписка 2025 (Russian Journal of Preventive Medicine)
 
МСФ на ЯМ
Close metadata
Recommended articles:
Risk asse­ssment of cardiovascular complications in unorganized popu­lation of the working-age men and women in the Vladimir region. Russian Journal of Preventive Medi­cine. 2023;(12):46-51
Long-term outcomes in patients with cardiovascular multimorbidity suffered from COVID-19: two-year obse­rvation. Russian Journal of Preventive Medi­cine. 2023;(12):58-64
Digi­tal healthcare of the Russian Fede­ration: basic concepts for practitioners. Russian Journal of Preventive Medi­cine. 2024;(1):97-105
Bili­rubin is a promising target for meta­bolic and athe­rosclerotic cardiovascular diseases. Russian Journal of Preventive Medi­cine. 2024;(1):121-127
Cardiac reha­bilitation: inve­stigation of effi­cacy, resu­lts, perspectives. Problems of Balneology, Physiotherapy and Exercise Therapy. 2023;(5):45-55
Non-invasive diagnosis of brain gliomas by histological type using neuroradiomics in standardized regions of inte­rest: towa­rds digi­tal biopsy. Burdenko's Journal of Neurosurgery. 2023;(6):59-66
Prospects for the use of robo­tic-assisted technologies in aesthetic plastic surgery. Plastic Surgery and Aesthetic Medi­cine. 2023;(4-2):24-34
Analysis of the need for magnetic reso­nance imaging in a multi-field hospital. Medi­cal Technologies. Asse­ssment and Choice. 2023;(4):19-25
Predictive model for addi­tional intraoperative placement of chest drainage after thoracoscopic lobe­ctomy. Piro­gov Russian Journal of Surgery. 2023;(12):14-25
Cell therapy in cardiology: a time for a hope. Russian Cardiology Bulletin. 2023;(4):7-18

The main ways to assess cardiovascular risk are SCORE, SCORE-2, Framingham scales, etc. However, these scales have several statistical drawbacks that may reduce their predictive value. Therefore, many researchers are encouraged to use machine learning technologies to predict cardiovascular risk.

OBJECTIVE

To compare the predictive value of the SCORE, Framingham and one of the machine learning methods based on the «INTEREPID» study.

MATERIAL AND METHODS

The study was conducted based on the data from the international prospective study «INTEREPID» conducted in 2011—2016 (n=2391). Endpoints: cases of coronary heart disease and acute cerebrovascular accident for Samara (n=253; 24.1%) and for the Kyrgyz Republic (n=280; 20.9%), total n=533 (22.5%). ExtraTreesClassifier was used as a machine learning algorithm for the Samara cohort, GradientBoostingClassifier for the Kyrgyz cohort and the entire «INTEREPID» cohort. The SCORE and the Framingham scales were used for comparison.

RESULTS

For the Samara cohort, the best AUC indicator is ExtraTreesClassifier — 0.609; for the Kyrgyz cohort — Framingham scale with an AUC of 0.828; and for the entire cohort, GradientBoostingClassifier with an AUC of 0.766.

CONCLUSION

The results of this study indicate that the quality of determination by the level of cardiovascular risk is better in most cases when using machine learning algorithms; however, in some cases, conflicting data were obtained. In both cases, attention should be paid to the quality of the sample based on which the mathematical model was built and the validation methods.

Keywords:

machine learning
cardiovascular risk
cardiovascular diseases
prediction
risk scales
artificial intelligence

Authors:

Mishkin I.A.

National Medical Research Center for Therapy and Preventive Medicine;
Kireevsk Central District Hospital

Kontsevaya A.V.

National Medical Research Center for Therapy and Preventive Medicine

Gusev A.V.

Russian Research Institute of Health;
K-SkAI

Saharov A.A.

Renaissance Insurance Group

Drapkina O.M.

National Medical Research Center for Therapy and Preventive Medicine;
A.I. Yevdokimov Moscow State University of Medicine and Dentistry

Received:

01.08.2023

Accepted:

08.09.2023

List of references:

  1. Kontsevaya AV, Drapkina OM, Balanova YuA, et al. Economic Burden of Cardiovascular Diseases in the Russian Federation in 2016. Ratsional’naya farmakoterapiya v kardiologii. 2018;14(2):156-166. (In Russ.). https://doi.org/10.20996/1819-6446-2018-14-2-156-166
  2. Drapkina OM, Kontsevaya AV, Kalinina AM, et al. Prevention of chronic non-communicable diseases in the Russian Federation. National Guide 2022. Kardiovaskulyarnaya terapiya i profilaktika. 2022;21(4):3235. (In Russ.). https://doi.org/10.15829/1728-8800-2022-3235
  3. Ukaz Prezidenta Rossijskoj Federatsii ot 07.05.2018 g. №204 «O natsional’nykh tselyakh i strategicheskikh zadachakh razvitiya Rossijskoj Federatsii na period do 2024 goda». (In Russ.). Accessed December 15, 2023. https://www.kremlin.ru/acts/bank/43027
  4. Organizatsiya provedeniya profilakticheskogo meditsinskogo osmotra i dispanserizatsii opredelennykh grupp vzroslogo naseleniya. Metodicheskie rekomendatsii po prakticheskoj realizatsii prikaza Minzdrava Rossii ot 13 marta 2019 g. №124n «Ob utverzhdenii poryadka provedeniya profilakticheskogo meditsinskogo osmotra i dispanserizatsii opredelennykh grupp vzroslogo naseleniya». M. 2019. (In Russ.).
  5. Conroy RM, Pyörälä K, Fitzgerald AP, et al. Estimation of ten-year risk of fatal cardiovascular disease in Europe: The SCORE project. European Heart Journal. 2003;24(11):987-1003. https://doi.org/10.1016/s0195-668x(03)00114-3
  6. SCORE2 working group and ESC Cardiovascular risk collaboration. SCORE2 risk prediction algorithms: new models to estimate 10-year risk of cardiovascular disease in Europe. European Heart Journal. 2021;42(25): 2439-2454. https://doi.org/10.1093/eurheartj/ehab309
  7. Belyalov FI. Prognozirovanie i shkaly v meditsine. 3-e izd., pererab. i dop. M.: MEDpress-inform; 2020. (In Russ.).
  8. Machin D, Cheung Y, Palmar M. Survival analysis: a practical approach. 2nd ed. New York; 2006.
  9. Sharashova EE, Kholmatova KK, Gorbatova MA, Grjibovski AM. Application of Cox regression in healthcare using the SPSS statistical software package. Nauka i zdravookhranenie. 2017;6:5-27. (In Russ.).
  10. Gusev AV, Gavrilov DV, Korsakov IN, et al. Prospects of using machine learning methods to predict cardiovascular diseases. Vrach i informatsionnye tekhnologii. 2019;(3):41-47. (In Russ.).
  11. Zhang Y, Guo SL, Han LN, Li TL. Application and Exploration of Big Data Mining in Clinical Medicine. Chinese Medical Journal. 2016;129(6):731-738.  https://doi.org/10.4103/0366-6999.178019
  12. Brink H. Real-world machine learning. Shelter Island, NY: Manning Publications Co.; 2017.
  13. Mishkin IA, Gusev AV, Kontsevaya AV, Drapkina O.M. mHealth apps as a tool for the prevention of cardiovascular diseases. Systematic review. Vrach i informatsionnye tekhnologii. 2022;4:12-27. (In Russ.). https://doi.org/10.25881/18110193_2022_4_12
  14. Mishkin IA, Koncevaya AV, Gusev AV, Drapkina OM. Prediction of cardiovascular events using proportional risk models and machine learning models: a systematic review. Sovremennye problemy zdravookhranenija i meditsinskoj statistiki. 2023;2:804-829. (In Russ.). https://doi.org/10.24412/2312-2935-2023-2-804-829
  15. Gusev AV, Gavrilov DV, Novitsky RE, et al. Improving the possibilities of assessing cardiovascular risk using machine learning methods. Rossijskij kardiologicheskij zhurnal. 2021;12:171-180. (In Russ.). https://doi.org/10.15829/1560-4071-2021-4618
  16. Wang Y, Zhu K, Li Y, et al. Comparison of Machine Learning Models and Framingham Risk Score for the prediction of the presence and severity of Coronary Artery Diseases by using Gensini Score. 2019. Accessed December 15, 2023. https://doi.org/10.21203/rs.2.12128/v1
  17. Sajeev S, Champion S, Beleigoli A, et al. Predicting Australian Adults at High Risk of Cardiovascular Disease Mortality Using Standard Risk Factors and Machine Learning. International Journal of Environmental Research and Public Health. 2021;18(6):3187. https://doi.org/10.3390/ijerph18063187
  18. Orfanoudaki A, Chesley E, Cadisch C, et al. Machine learning provides evidence that stroke risk is not linear: The non-linear Framingham stroke risk score. PLoS One. 2020;15(5):e0232414. https://doi.org/10.1371/journal.pone.0232414
  19. Dimopoulos AC, Nikolaidou M, Caballero FF, et al. Machine learning methodologies versus cardiovascular risk scores, in predicting disease risk. BMC Medical Research Methodology. 2018;18(1):179.  https://doi.org/10.1186/s12874-018-0644-1
  20. Gusev AV, Vladzimirsky AV, Sharova DE, et al. Development of research and development in the field of artificial intelligence technologies for healthcare in the Russian Federation: results of 2021. Digital Diagnostics. 2022; 3(3):178-194. (In Russ.). https://doi.org/10.17816/DD107367
  21. mHealth Apps Market Size Worth $149.3 Billion By 2028 | CAGR: 17.7%. Grand View Research, Inc. Accessed December 15, 2023. https://www.prnewswire.com/news-releases/mhealth-apps-market-size-worth-149-3-billion-by-2028--cagr-17-7-grand-view-research-inc-301233046.html

Close metadata

Contact the author
Email
Message
The publishing house "Media Sphere" does not provide treatment services, does not give recommendations on contacting medical institutions and specific specialists, on the prescription of medicines and dietary supplements.

Email Confirmation

An email was sent to test@gmail.com with a confirmation link. Follow the link from the letter to complete the registration on the site.

Email Confirmation

Contact us
If you have any questions, complaints or suggestions, please use this feedback form.
Email
Message
The publishing house "Media Sphere" does not provide treatment services, does not give recommendations on contacting medical institutions and specific specialists, on the prescription of medicines and dietary supplements.
Submit Application

You can become an author of one of our magazines, send a request and we will consider it in during the day.

Name
Phone
E-mail
Message
Login
Registration
E-mail
Password
Forgot Password?

Log in to the site using your account in one of the services

Password recovery
E-mail
Login
Register


We use cооkies to improve the performance of the site. By staying on our site, you agree to the terms of use of cооkies. To view our Privacy and Cookie Policy, please. click here.